BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20190731T213613Z
LOCATION:Wrigley
DTSTART;TZID=America/Chicago:20190730T160000
DTEND;TZID=America/Chicago:20190730T163000
UID:pearc_PEARC19_sess187_pap149@linklings.com
SUMMARY:Expanding the Computational Anatomy Gateway from clinical imaging 
 to basic neuroscience research
DESCRIPTION:Expanding the Computational Anatomy Gateway from clinical imag
 ing to basic neuroscience research\n\nTward, Kolasny, Kahn, Troncoso, Mill
 er\n\nThe Computational Anatomy Gateway, powered largely by the Comet (San
  Diego Supercomputer Center) and Stampede (Texas Advanced Computing Center
 ) clusters through XSEDE, provides software as a service tools for atlas b
 ased analysis of human brain magnetic resonance images.  This includes def
 ormable registration, automatic labeling of tissue types, and morphometric
  analysis.  Our goal is to extend these services to the broader neuroscien
 ce community, accommodating multiple model organisms and imaging modalitie
 s, as well as low quality or missing data.  We developed a new approach to
  multimodality registration: by predicting one modality from another, we c
 an replace ad hoc image similarity metrics (such as mutual information or 
 normalized cross correlation) with a log likelihood under a noise model.  
 This statistical approach enables us to account for missing data using the
  Expectation Maximization algorithm.  For portability and scalability we h
 ave implemented this algorithm in tensorflow.  For accessibility we have c
 ompiled and many working examples for multiple model organisms, imaging sy
 stems, and missing tissue or image anomaly situations.  These examples are
  made easily usable in the form of Jupyter notebooks, and made publicly av
 ailable through github.  This framework will significantly reduce the barr
 ier to entry for basic neuroscientists, enabling the community to benefit 
 from atlas based computational image analysis techniques.\n\nPaper\nTechni
 cal Paper, Applications, Science Gateways
URL:https://pearc19.conference-program.com/presentation/?id=pap149&sess=se
 ss187
END:VEVENT
END:VCALENDAR

